Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish the safety profile (write, non-destructive, non-idempotent, closed world). The description adds genuinely new behavior: WORLD_EVENT items are verified against the case's world, unknown event IDs are rejected, an API key is required, and the per-side quota is 10. It does not say what happens when the quota is exceeded or on verification failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Compact and front-loaded: the core action leads, and constraints follow in a tight parenthetical. The dense parenthetical packs several distinct rules into one sentence, which costs a little readability but no sentence is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a write tool with no output schema, the description covers the important context an agent needs: auth requirement, quota, verification semantics, and staging rules. Remaining gaps (quota-exceeded behavior, error/response shape) are secondary given the rich input schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the evidence field already documents the three variants and their meanings in detail. The description adds only marginal semantics ('unknown event IDs are rejected', the 10-item cap) on top of that, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Add one item of evidence for your side') plus scope constraints (one item per call, up to 10 per side), so an agent can tell it apart from withdraw_evidence or make_statement in practice. However, it never names an adjacent tool, so the differentiation is implicit rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives real usage context: it applies in 'evidence stages' and notes the defence may also attach evidence to its response, plus a 10-item-per-side cap. It stops short of stating when-not to use it (e.g., to remove an item, use withdraw_evidence; for a party's own account, make_statement).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.